claude-plugins

This skill should be used for Claude Code permission rules, modes, settings, MCP permission syntax, and hooks boundaries. Do not use it as the authorization contract for Claude Platform memory, bash, text-editor, computer-use, server tools, or Messages API handlers.

Use when designing or troubleshooting Claude Platform tool contracts: names, descriptions, input_schema, input_examples, strict, tool_choice, cache/privacy, versions, and routing boundaries.

Performs structured trade-off analysis using weighted scoring matrices, decision matrices, and ATAM (Architecture Tradeoff Analysis Method) to make defensible architectural and technology decisions. [EXPLICIT] Trigger: 'trade-off', 'decision matrix', 'ATAM', 'weighted scoring', 'pros and cons'

UX writing and document accessibility standards for technical deliverables. Use when the user asks to 'improve readability', 'fix information hierarchy', 'reduce cognitive load', 'write microcopy', 'check readability score', or mentions 'UX writing', 'scanability', 'Flesch-Kincaid', 'escritura UX', 'legibilidad', 'cognitive load'. [EXPLICIT]

Build and deploy on Vercel: Edge and Serverless Functions, Vercel Postgres/Neon, KV, Blob storage, environment secrets, Incremental Static Regeneration, and deploy via CLI. [EXPLICIT] One of the three target platforms (Firebase + Vercel + Hostinger). Trigger: 'vercel', 'edge function', 'vercel deploy', 'vercel postgres', 'ISR', 'next on vercel'.

Provider-agnostic web infrastructure: DNS architecture, SSL/TLS certificate lifecycle, CDN and edge optimization, backup and disaster recovery, domain lifecycle. [EXPLICIT] Cross-cuts Firebase/Vercel/Hostinger. Trigger: 'dns', 'ssl', 'tls', 'cdn', 'backup', 'disaster recovery', 'rto', 'rpo', 'domain'.

This skill should be used when the user asks to scrape a web page, crawl a site, search the web, extract structured data from URLs, or run deep web research on a topic.

This skill should be used when the user asks to isolate Claude Code work with git worktrees, run Claude Code with --worktree or -w, configure .worktreeinclude, add WorktreeCreate or WorktreeRemove hooks, set worktree.baseRef, run subagents with isolation: worktree, clean up .claude/worktrees, use EnterWorktree, or avoid file conflicts between parallel sessions.